Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 250 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.2850. Min Range: -0.2850

Max Act: 0.2850. Min Act: -0.0000

Data Index: 49197 (C4 (Web Text))

Max Activating Token Index: 837

Text #1

Max Range: 0.2850. Min Range: -0.2850

Max Act: 0.2696. Min Act: -0.0000

Data Index: 228702 (C4 (Web Text))

Max Activating Token Index: 641

Text #2

Max Range: 0.2850. Min Range: -0.2850

Max Act: 0.2681. Min Act: -0.0000

Data Index: 265092 (C4 (Web Text))

Max Activating Token Index: 771

Text #3

Max Range: 0.2850. Min Range: -0.2850

Max Act: 0.2705. Min Act: -0.0000

Data Index: 839370 (C4 (Web Text))

Max Activating Token Index: 755

Text #4

Max Range: 0.2850. Min Range: -0.2850

Max Act: 0.2551. Min Act: -0.0000

Data Index: 310012 (C4 (Web Text))

Max Activating Token Index: 783

Text #5

Max Range: 0.2850. Min Range: -0.2850

Max Act: 0.2649. Min Act: -0.0000

Data Index: 952715 (C4 (Web Text))

Max Activating Token Index: 180

Text #6

Max Range: 0.2850. Min Range: -0.2850

Max Act: 0.2445. Min Act: -0.0000

Data Index: 184904 (C4 (Web Text))

Max Activating Token Index: 191

Text #7

Max Range: 0.2850. Min Range: -0.2850

Max Act: 0.2598. Min Act: -0.0000

Data Index: 1219355 (C4 (Web Text))

Max Activating Token Index: 627

Text #8

Max Range: 0.2850. Min Range: -0.2850

Max Act: 0.2393. Min Act: -0.0000

Data Index: 1074892 (C4 (Web Text))

Max Activating Token Index: 384

Text #9

Max Range: 0.2850. Min Range: -0.2850

Max Act: 0.2374. Min Act: -0.0000

Data Index: 534181 (C4 (Web Text))

Max Activating Token Index: 616

Text #10

Max Range: 0.2850. Min Range: -0.2850

Max Act: 0.2443. Min Act: -0.0000

Data Index: 252531 (C4 (Web Text))

Max Activating Token Index: 788

Text #11

Max Range: 0.2850. Min Range: -0.2850

Max Act: 0.2450. Min Act: -0.0000

Data Index: 80090 (C4 (Web Text))

Max Activating Token Index: 331

Text #12

Max Range: 0.2850. Min Range: -0.2850

Max Act: 0.2364. Min Act: -0.0000

Data Index: 1123571 (C4 (Web Text))

Max Activating Token Index: 969

Text #13

Max Range: 0.2850. Min Range: -0.2850

Max Act: 0.2499. Min Act: -0.0000

Data Index: 1087322 (C4 (Web Text))

Max Activating Token Index: 802

Text #14

Max Range: 0.2850. Min Range: -0.2850

Max Act: 0.2308. Min Act: -0.0000

Data Index: 10012 (C4 (Web Text))

Max Activating Token Index: 97

Text #15

Max Range: 0.2850. Min Range: -0.2850

Max Act: 0.2435. Min Act: -0.0000

Data Index: 590707 (C4 (Web Text))

Max Activating Token Index: 663

Text #16

Max Range: 0.2850. Min Range: -0.2850

Max Act: 0.2329. Min Act: -0.0000

Data Index: 1289267 (C4 (Web Text))

Max Activating Token Index: 299

Text #17

Max Range: 0.2850. Min Range: -0.2850

Max Act: 0.2303. Min Act: -0.0000

Data Index: 346599 (C4 (Web Text))

Max Activating Token Index: 28

Text #18

Max Range: 0.2850. Min Range: -0.2850

Max Act: 0.2293. Min Act: 0.0000

Data Index: 166814 (C4 (Web Text))

Max Activating Token Index: 49

Text #19

Max Range: 0.2850. Min Range: -0.2850

Max Act: 0.2262. Min Act: -0.0000

Data Index: 1178060 (C4 (Web Text))

Max Activating Token Index: 853